Driver Drowsiness Detection Using Eye Movement Behavior

Drowsy driving is a critical threat to road safety, being the cause of a large proportion of traffic accidents every year. This study examines the use of eye movement behaviour as a promising indicator for identifying driver drowsiness. Through the use of a blend of machine learning algorithms and eye-tracking technology, we examine eye movement patterns such as blink rate, gaze duration, and pupil dilation in order to create a real-time monitoring system. Our research employs a dataset of data gathered in simulated driving conditions, where subjects were subjected to pre-determined levels of fatigue. Our results show that certain eye movement measures are highly correlated with levels of drowsiness, enabling the creation of a model to predict when drivers will be fatigued and alert them in advance of reaching the point of critical fatigue. The system proposed here not only shows high accuracy in detecting drowsiness but also has the potential to be integrated into current vehicle safety systems. This work advances the field of driver safety by presenting a new, non-intrusive way of monitoring driver alertness and minimizing the number of drowsy driving accidents